Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    trends or changes in numerical values

    oai_token-act-pair · gpt-3.5-turbo

    changes in numerical values or percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbn
    -0.81
    ndra
    -0.76
    etary
    -0.70
    swick
    -0.69
    etsk
    -0.67
    gemony
    -0.65
    esson
    -0.63
    orsche
    -0.60
    èĪ
    -0.59
    engeance
    -0.59
    POSITIVE LOGITS
     from
    0.97
     to
    0.94
    from
    0.87
     dramatically
    0.86
     steadily
    0.85
    to
    0.84
     drastically
    0.80
     sharply
    0.77
     exponentially
    0.77
     astron
    0.76
    Act Density 0.219%

    No Known Activations